Defect detection in objects using statistical approaches

Abstract

Disclosed are systems, methods and articles, including an inspection system that includes at least one generator to apply energy to an object at an application point to cause waves to travel, at least partly, through the object. The system further includes at least one detector configured to detect at least a portion of the waves traveling through the object, and a statistical analyzer to perform a statistical analysis based on an output produced by the at least one detector in response to the detected portion of the waves, the statistical analysis being used to determine whether at least one defect is present in the object.

What is claimed is: 
     
       1. A system comprising:
 at least one generator configured to apply energy to an object at an application point to cause waves to travel, at least partly, through the object; 
 at least one detector configured to detect at least a portion of the waves traveling through the object; and 
 a statistical analyzer configured to perform a statistical analysis based on an output produced by the at least one detector in response to the detected portion of the waves, the statistical analysis being used to determine whether at least one defect is present in the object, wherein the statistical analysis performs on the output of the at least one detector one or more of an outlier analysis, a discordancy test, and an anomaly detection, by at least computing one or more variation values between feature values of the detected portion of the waves and corresponding baseline feature values computed for a defect-free section of a representative object having a profile substantially similar to the profile of the object, and 
 wherein the feature values include one or more of a root-mean square of an amplitude of the detected portion of the waves, a variance of the amplitude of the detected portion of the waves, a cross-correlation value of the amplitude of the detected portion of the waves, an auto-correlation value of the amplitude of the detected portion of the waves, a peak-to-peak value of the amplitude of the detected portion of the waves, a peak value of the amplitude of the detected portion of the waves, a Kurtosis value of the amplitude of the detected portion of the waves, a time-domain statistical moment corresponding to properties of the detected portion of the waves, a frequency-domain statistical moment corresponding to the properties of the detected portion of the waves, and one or more normalized values of one or more of the feature values. 
 
     
     
       2. The system of  claim 1 , wherein the statistical analyzer configured to compute the one or more variation values between feature values of the detected portion of the waves and the corresponding baseline feature values is configured to at least: compute a value based on the equation:
   Mahalanobis Squared Distance (M.S.D.)=( x−  x   ) T   ×Cov   −1 ×( x−  x   )
 
 where x is a vector of the computed feature values, is the mean vector of the corresponding baseline feature values, represents a covariance matrix operation, T represents a transpose operation and −1 represents an inverse matrix operation. 
 
     
     
       3. The system of  claim 1 , wherein the object includes a rail of a railroad track, and wherein the at least one defect includes an internal crack in the rail. 
     
     
       4. The system of  claim 1 , wherein the at least one generator includes the at least one detector. 
     
     
       5. The system of  claim 1 , wherein the at least one generator is configured to at least apply energy to the object at a moving application point. 
     
     
       6. The system of  claim 1 , wherein the at least one generator to apply energy to the object is configured to at least:
 apply energy to cause acoustic bulk waves, including one or more of longitudinal waves and shear waves, to travel through the object at specified angles to enhance the defect detection sensitivity. 
 
     
     
       7. The system of  claim 1 , wherein the at least one detector is configured to at least detect the portion of the waves within a pre-determined time window. 
     
     
       8. The system of  claim 7 , wherein the statistical is configured to at least:
 determine one or more variation values between features of respective portions of bulk waves detected by the at least one detector. 
 
     
     
       9. The system of  claim 1 , further including at least one device configured to act as the generator and the detector. 
     
     
       10. The system of  claim 1 , wherein the at least one generator is configured to at least:
 apply energy to cause acoustic waves having one or more components with corresponding frequencies to travel through the object to enhance the defect detection sensitivity at one or more object depths. 
 
     
     
       11. The system of  claim 1 , wherein the at least one generator includes one or more of: an ultrasonic wheel generator, an ultrasonic sled generator, a water-coupled generator, a laser acoustic device, air-coupled transducer, an electro-magnetic acoustic transducer (EMAT) and a mechanical impactor. 
     
     
       12. The system of  claim 1 , wherein the at least one generator is contained in a first wheel and the at least one detector is contained in a second wheel. 
     
     
       13. The system of  claim 1 , wherein the at least one generator comprises a first piezoelectric transducer contained in a first wheel configured to roll on a rail and to induce in the rail at least one of a plurality of first ultrasonic guided waves, and the at least one detector comprises a second piezoelectric transducer contained in a second wheel configured to roll on the rail and to detect at least one of a plurality of second ultrasonic guided waves propagating in the rail. 
     
     
       14. The system of  claim 13 , wherein the first wheel and the second wheel each include an inner cylindrical cavity containing a fluid. 
     
     
       15. The system of  claim 13 , wherein the at least one of the plurality of first ultrasonic guided waves travels in a direction substantially parallel to a longitudinal axis of the rail. 
     
     
       16. The system of  claim 13 , wherein the at least one of the plurality of second ultrasonic guided waves travels in a direction substantially parallel to a longitudinal axis of the rail. 
     
     
       17. The system of  claim 12 , wherein the first wheel and the second wheel are the same wheel. 
     
     
       18. The system of  claim 12 , wherein the first wheel and the second wheel are separate wheels. 
     
     
       19. A method comprising:
 applying energy to an object at an application point to cause resultant waves to travel, at least partly, through the object; 
 detecting at least a portion of the waves traveling through the object; and 
 performing, by a statistical analyzer, a statistical analysis based on output produced in response to the detected portion of the waves, the statistical analysis being used to determine whether at least one defect is present in the object, wherein the statistical analysis performs on the output of the at least one detector one or more of an outlier analysis, a discordancy test, and an anomaly detection, by at least computing one or more variation values between feature values of the detected portion of the waves and corresponding baseline feature values computed for a defect-free section of a representative object having a profile substantially similar to the profile of the object, and 
 wherein the feature values include one or more of a root-mean square of an amplitude of the detected portion of the waves, a variance of the amplitude of the detected portion of the waves, a cross-correlation value of the amplitude of the detected portion of the waves, an auto-correlation value of the amplitude of the detected portion of the waves, a peak-to-peak value of the amplitude of the detected portion of the waves, a peak value of the amplitude of the detected portion of the waves, a Kurtosis value of the amplitude of the detected portion of the waves, a time-domain statistical moment corresponding to properties of the detected portion of the waves, a frequency-domain statistical moment corresponding to the properties of the detected portion of the waves, and one or more normalized values of one or more of the feature values. 
 
     
     
       20. The method of  claim 19 , wherein computing one or more variation values comprises:
 computing a value based on the equation:
   Mahalanobis Squared Distance (M.S.D.)=( x−  x   ) T   ×Cov   −1 ×( x−  x   )
 
 
 where x is a vector of the computed feature values, is the mean vector of the corresponding baseline feature values, represents a covariance matrix operation, T represents a transpose operation and −1 represents an inverse matrix operation. 
 
     
     
       21. The method of  claim 19 , wherein applying energy to the object comprises: applying energy to cause acoustic waves having one or more components with corresponding frequencies to travel through the object to enhance the defect detection sensitivity at one or more object depths. 
     
     
       22. The method of  claim 19 , wherein detecting the portion of the waves comprises:
 detecting portions of the waves by two or more detectors positioned at one of: different sides of the application point and on the same side of the application point. 
 
     
     
       23. The method of  claim 19 , wherein the feature values include one or more of:
 a root-mean square of an amplitude of the detected portion of the waves, a variance of the amplitude of the detected portion of the waves, a cross-correlation value of the amplitude of the detected portion of the waves, an auto-correlation value of the amplitude of the detected portion of the waves, a peak-to-peak value of the amplitude of the detected portion of the waves, a peak value of the amplitude of the detected portion of the waves, a Kurtosis value of the amplitude of the detected portion of the waves, a time-domain statistical moment corresponding to properties of the detected portion of the waves, a frequency-domain statistical moment corresponding to the properties of the detected portion of the waves, and one or more normalized values of one or more of the feature values. 
 
     
     
       24. The method of  claim 19 , wherein applying energy to the object comprises:
 applying energy to cause acoustic bulk waves, including one or more of longitudinal waves and shear waves, to travel through the object at specified angles to enhance the defect detection sensitivity. 
 
     
     
       25. A non-transitory computer program product residing on a computer readable medium and comprising computer instructions that when executed on a processor-based device cause the processor-based device to at least:
 perform a statistical analysis based on output produced in response to detected at least a portion of waves traveling through an object, the statistical analysis being used to determine whether at least one defect is present in the object, a statistical analyzer configured to perform a statistical analysis based on an output produced by the at least one detector in response to the detected portion of the waves, the statistical analysis being used to determine whether at least one defect is present in the object, wherein the statistical analysis performs on the output of the at least one detector one or more of an outlier analysis, a discordancy test, and an anomaly detection, by at least computing one or more variation values between feature values of the detected portion of the waves and corresponding baseline feature values computed for a defect-free section of a representative object having a profile substantially similar to the profile of the object, 
 wherein the feature values include one or more of a root-mean square of an amplitude of the detected portion of the waves, a variance of the amplitude of the detected portion of the waves, a cross-correlation value of the amplitude of the detected portion of the waves, an auto-correlation value of the amplitude of the detected portion of the waves, a peak-to-peak value of the amplitude of the detected portion of the waves, a peak value of the amplitude of the detected portion of the waves, a Kurtosis value of the amplitude of the detected portion of the waves, a time-domain statistical moment corresponding to properties of the detected portion of the waves, a frequency-domain statistical moment corresponding to the properties of the detected portion of the waves, and one or more normalized values of one or more of the feature values, and 
 wherein the waves are produced by applying energy to the object at an application point. 
 
     
     
       26. The non-transitory computer-program product of  claim 25 , wherein the instructions that cause the processor-based device to compute the one or more variation values comprise instructions that cause the processor-based device to at least:
 compute a value based on the equation:
   Mahalanobis Squared Distance (M.S.D.)=( x−  x   ) T   ×Cov   −1 ×( x−  x   )
 
 
 where x is a vector of the computed feature values, is the mean vector of the corresponding baseline feature values, represents a covariance matrix operation, T represents a transpose operation and −1 represents an inverse matrix operation. 
 
     
     
       27. The non-transitory computer program product of  claim 25 , wherein the instructions further comprise instructions to cause the processor-based device to at least:
 cause the energy to be applied to the object to cause acoustic bulk waves, including one or more of longitudinal waves and shear waves, to travel through the object at specified angles to enhance the defect detection sensitivity. 
 
     
     
       28. A system comprising:
 at least one generator configured to apply energy to an object at an application point to cause waves to travel, at least partly, through the object; 
 at least one detector configured to detect at least a portion of the waves traveling through the object, wherein the at least one detector includes two or more acoustic detectors positioned at one of different sides of the application point or on the same side of the application point, and wherein the two or more acoustic detectors are configured to detect guided waves portions resulting from the energy applied to the object, the guided waves portions traveling at a direction substantially parallel to the longitudinal axis of the object; and 
 a statistical analyzer configured to perform a statistical analysis based on an output produced by the at least one detector in response to the detected portion of the waves, the statistical analysis being used to determine whether at least one defect is present in the object. 
 
     
     
       29. The system of  claim 28 , wherein the statistical analyzer is configured to at least:
 determine one or more variation values between features of the respective portions of the guided waves detected by the two or more detectors. 
 
     
     
       30. The system of  claim 29 , wherein the statistical analyzer is configured to at least:
 compute ratio values of the features of the respective detected portions of the guided waves. 
 
     
     
       31. A method comprising:
 applying, by at least one generator, energy to an object at an application point to cause waves to travel, at least partly, through the object; 
 detecting, by at least one detector, at least a portion of the waves traveling through the object, wherein the at least one detector includes two or more acoustic detectors positioned at one of different sides of the application point or on the same side of the application point, and wherein the two or more acoustic detectors are configured to detect guided waves portions resulting from the energy applied to the object, the guided waves portions traveling at a direction substantially parallel to the longitudinal axis of the object; and 
 performing, by a statistical analyzer, a statistical analysis based on an output produced by the at least one detector in response to the detected portion of the waves, the statistical analysis being used to determine whether at least one defect is present in the object. 
 
     
     
       32. A non-transitory computer program product residing on a computer readable medium and comprising computer instructions that when executed on a processor-based device cause the processor-based device to at least:
 apply energy to an object at an application point to cause waves to travel, at least partly, through the object; 
 detect at least a portion of the waves traveling through the object, wherein the at least one detector includes two or more acoustic detectors positioned at one of different sides of the application point or on the same side of the application point, and wherein the two or more acoustic detectors are configured to detect guided waves portions resulting from the energy applied to the object, the guided waves portions traveling at a direction substantially parallel to the longitudinal axis of the object; and 
 perform a statistical analysis based on an output produced by the at least one detector in response to the detected portion of the waves, the statistical analysis being used to determine whether at least one defect is present in the object.